Notion launches agents for data analysis and task automation

During the “Make With Notion” event on Thursday, the company announced the launch of his first AI agent. The agent uses all noteping pages and database of a user as a context, which automatically generates notes and analysis for meetings, evaluation reports from competitors and feedback destination pages.

The productivity platform said that the agent can make pages and databases, or can update them with new data, properties or views. Users can also activate notion agents of external platforms that are linked to the service. For example, you can ask the Notion Agent to create a bug -tracking -dashboard from different sources, including Slack, E -mail and Google Drive.

The newly announced agent builds on Notion Ai, an existing function that can search or summarize content. But the new agent is able to tackle more complex Multi-Step tasks, using the powers of Agentic AI. The company said that the current version of Agent can perform a task that runs for up to 20 minutes on hundreds of pages.

Users can set a “profile” page for the agent to instruct it to follow instructions when referring to sources, output style and where you update tasks and end results. You can also ask the agent to ‘remember’ important points while people use them. Those memories are stored on the profile page and users can edit them there.

In Demo videos, the company gave examples of agents who could give feedback for destination pages and update, make a restaurant tracker, make an analysis of meeting notes and prepare a competition analysis report.

At the moment you have to manually activate these promotions. But Notion said that the possibility to make tailor -made agents who work on a schedule or triggers will soon come. The company will also release a template library for agents, so that you can choose ready-made prompts that may match your task.

In the past two years, Notion has released an agenda app, a Gmail client, a meetingman and a search from Enterprise to get information from different sources. These are functions that the company has given sufficient contextual building blocks to make automation. Other Enterprise Knowledge and Productivity Platforms, including Salesforce, Fireflies, Read AI have launched their own agents to extract and update information.